Learning Structured Embeddings of Knowledge Graphs with Adversarial Learning Framework

TL;DR

This paper introduces an adversarial learning framework for embedding knowledge graphs into continuous vector spaces, enabling better link prediction and triple classification by generating and discriminating triples.

Contribution

It proposes a novel generative adversarial network approach that improves knowledge graph embeddings and can generate unseen instances, enhancing existing relational models.

Findings

Significant improvement over classical models like TransE in link prediction.

Effective generation of unseen triples for knowledge graph completion.

Enhanced triple classification accuracy.

Abstract

Many large-scale knowledge graphs are now available and ready to provide semantically structured information that is regarded as an important resource for question answering and decision support tasks. However, they are built on rigid symbolic frameworks which makes them hard to be used in other intelligent systems. We present a learning method using generative adversarial architecture designed to embed the entities and relations of the knowledge graphs into a continuous vector space. A generative network (GN) takes two elements of a (subject, predicate, object) triple as input and generates the vector representation of the missing element. A discriminative network (DN) scores a triple to distinguish a positive triple from those generated by GN. The training goal for GN is to deceive DN to make wrong classification. When arriving at a convergence, GN recovers the training data and can be used for knowledge graph completion, while DN is trained to be a good triple classifier. Unlike few previous studies based on generative adversarial architectures, our GN is able to generate unseen instances while they just use GN to better choose negative samples (already existed) for DN. Experiments demonstrate our method can improve classical relational learning models (e.g.TransE) with a significant margin on both the link prediction and triple classification tasks.